Reading List for Human-Compatible AI Research
Under construction; last updated 2016-12-06 03:28:58 PDT...
Read more »A new way to train AI systems could keep them safer from hackers
Deep-learning-based methods for different applications have been shown
vulnerable to adversarial examples. These examples make deployment of such
models in safety-critical tasks questionable. Use of deep neural networks as
inverse problem solvers has gene… Read more